cs.CV（2024-01-03）

📊 共 19 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (8 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (5 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱六：视频提取与匹配 (Video Extraction) (1 🔗1) 支柱一：机器人控制 (Robot Control) (1) 支柱五：交互与反应 (Interaction & Reaction) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (8 篇)

#题目一句话要点标签🔗⭐
1 Moonshot: Towards Controllable Video Generation and Editing with Multimodal Conditions 提出Moonshot以解决视频生成控制不足的问题 multimodal ✅
2 Few-shot Adaptation of Multi-modal Foundation Models: A Survey 提出少样本适应方法以提升多模态基础模型性能 foundation model
3 WordArt Designer API: User-Driven Artistic Typography Synthesis with Large Language Models on ModelScope 提出WordArt Designer API以解决非专业用户艺术排版设计问题 large language model
4 Transformer RGBT Tracking with Spatio-Temporal Multimodal Tokens 提出一种新型Transformer RGBT跟踪方法以应对目标外观变化问题 multimodal
5 Prototypical Information Bottlenecking and Disentangling for Multimodal Cancer Survival Prediction 提出原型信息瓶颈与解耦方法以解决多模态癌症生存预测中的冗余问题 multimodal
6 Towards Truly Zero-shot Compositional Visual Reasoning with LLMs as Programmers 提出一种框架以解决视觉推理中的人力工程问题 large language model visual grounding
7 HawkRover: An Autonomous mmWave Vehicular Communication Testbed with Multi-sensor Fusion and Deep Learning 提出HawkRover以解决毫米波车辆通信中的信号衰减问题 multimodal
8 Incorporating Geo-Diverse Knowledge into Prompting for Increased Geographical Robustness in Object Recognition 提出地理多样知识以增强物体识别的地理鲁棒性 large language model

🔬 支柱三：空间感知与语义 (Perception & Semantics) (5 篇)

#题目一句话要点标签🔗⭐
9 FMGS: Foundation Model Embedded 3D Gaussian Splatting for Holistic 3D Scene Understanding 提出FMGS以解决3D场景理解中的几何与语义感知问题 3D gaussian splatting gaussian splatting splatting
10 SIGNeRF: Scene Integrated Generation for Neural Radiance Fields 提出SIGNeRF以解决3D场景编辑与生成问题 NeRF neural radiance field
11 LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry 提出LEAP-VO以解决动态场景下视觉里程计问题 visual odometry
12 DDN-SLAM: Real-time Dense Dynamic Neural Implicit SLAM 提出DDN-SLAM以解决动态环境下的SLAM问题 NeRF scene reconstruction
13 S3Net: Innovating Stereo Matching and Semantic Segmentation with a Single-Branch Semantic Stereo Network in Satellite Epipolar Imagery 提出S3Net以解决卫星立体影像中的立体匹配与语义分割问题 3D reconstruction ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
14 Enhancing Representation in Medical Vision-Language Foundation Models via Multi-Scale Information Extraction Techniques 提出多尺度信息提取技术以提升医学视觉语言基础模型表现 representation learning foundation model
15 Multimodal self-supervised learning for lesion localization 提出多模态自监督学习以解决病灶定位问题 contrastive learning multimodal
16 MLIP: Medical Language-Image Pre-training with Masked Local Representation Learning 提出MLIP框架以解决医学图像文本配对数据稀缺问题 representation learning contrastive learning

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
17 STAF: 3D Human Mesh Recovery from Video with Spatio-Temporal Alignment Fusion 提出STAF模型以解决3D人类网格恢复中的时空信息缺失问题 human mesh recovery human motion ✅

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
18 Learning Keypoints for Robotic Cloth Manipulation using Synthetic Data 提出合成数据管道以解决机器人布料操控问题 manipulation sim-to-real

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#题目一句话要点标签🔗⭐
19 From Audio to Photoreal Embodiment: Synthesizing Humans in Conversations 提出一种框架以合成对话中的逼真全身虚拟人 dyadic interaction

⬅️ 返回 cs.CV 首页 · 🏠 返回主页